work-branch-name-gen
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes a shell script named
df-tifrom the user's localdotfiles/bindirectory. The arguments passed to this script are validated to ensure they are strictly decimal issue numbers, which effectively mitigates command injection risks. - [INDIRECT_PROMPT_INJECTION]: The skill processes data fetched from an external source (issue titles and descriptions retrieved by the
df-ticommand). - Ingestion points: The output of the
df-ticommand is used to derive branch descriptions. - Boundary markers: No specific delimiters or warnings are used to isolate the fetched issue content from the instructions.
- Capability inventory: The skill is limited to shell execution of the specific
df-tiutility. - Sanitization: The skill enforces a strict output format for the generated branch name (kebab-case, lowercase ASCII letters, digits, and hyphens), which prevents malicious content from the issue details from influencing subsequent shell commands or file operations using the generated branch name.
Audit Metadata